We introduce Martingale Doppelgänger-Eval, a public shadow-market benchmark for auditing whether vision-language models (VLMs) use candlestick evidence rather than extrapolate past trends. The central difficulty is identification: on real market histories, chart evidence and trend are strongly coupled, so an observational score cannot determine whether a fluent technical-analysis narrative is grounded in local visual evidence. We prove this limitation formally: no evaluation functional computed from observational chart--label data can distinguish a grounded responder from a trend-shortcut responder under strong coupling, whereas matched evidence interventions separate the same responders at an exponential rate and trend--label swaps provide an independent shortcut stress test. The benchmark therefore evaluates frozen VLMs on rendered OHLCV charts under four controlled mechanisms: a martingale-null market, injected-alpha counterfactual pairs, trend-confounder swaps, and regime shifts. A structural behavioral model identifies null-market bias, trend sensitivity, evidence sensitivity, prompt/renderer fragility, and evidence faithfulness; the accompanying statistical toolkit provides minimum detectable effects, block-aware sequential testing for metered APIs, and an overlap-weighted artifact check. Across frozen commercial and open VLMs, the identified regression assigns large positive coefficients to past trend but evidence coefficients that are zero or opposite to the rule-implied sign. Matched-pair analyses show that models either ignore injected candlestick semantics or move opposite to the rule-implied direction conditional on responding. The benchmark isolates a failure mode that standard observational chart benchmarks cannot detect and gives a reusable audit template for time-series imagery with controllable label mechanisms.

Agentic artificial intelligence systems introduce a new class of model risk. Unlike traditional predictive models, autonomous agents continuously acquire information, form beliefs regarding latent states of the environment, generate forecasts, select actions, and adapt their behavior over time. Existing validation methodologies focus primarily on predictive accuracy and therefore provide limited insight into the quality of the underlying decision process. This paper proposes a model validation framework for agentic AI based on Partially Observable Markov Decision Processes (POMDPs). The framework decomposes autonomous decision making into information, beliefs, forecasts, actions, and utility, allowing each component to be validated independently. Large language models (LLMs) are formalized as approximate Bayesian filtering operators, and a model-risk taxonomy is developed encompassing state-space, filtering, forecast, policy, utility-specification, and parameter risks. The model risk validation methodology is demonstrated through a portfolio-management case study in which an agent infers latent market regimes from market and macroeconomic information, generates belief-conditioned forecasts, and constructs portfolios using a Black--Litterman framework. Empirical validation combines performance analysis, belief calibration diagnostics, coverage tests, ablation studies, and parameter-sensitivity analysis. The results indicate that latent-state inference contributes independently to decision quality and that the principal conclusions remain robust across a broad range of parameter values. The principal contribution of the paper is a practical framework for extending established model risk management concepts to autonomous AI systems and providing a rigorous foundation for their validation, governance, and monitoring.

Modern option-learning systems operate in two coordinates: price space, where markets quote and no-arbitrage constraints are most naturally enforced, and implied volatility (IV) space, where volatility surfaces are smoothed, regularized, and evaluated. The bottleneck is interface, not approximation: Jäckel's seminal "Let's Be Rational" (LBR) solver already inverts the Black-Scholes price to machine precision efficiently. What is missing is a differentiable layer that preserves LBR in the forward pass and avoids backpropagating through its branch logic. Such a layer must also confront the unavoidable singularity of the inverse map in the low-vega regime, where the sensitivity 1/vega diverges as vega -> 0. We close this gap with PIVOT, the Price-Implied-Volatility Objective Translator. PIVOT keeps the LBR forward pass intact and supplies the backward pass by implicit differentiation through the smooth Black-Scholes/Black-76 price map, with an explicit gating contract: invalid domains return NaN, well-conditioned rows receive the exact 1/vega gradient, and low-vega rows are attenuated rather than silently regularized. On a single H100, a fused Triton kernel reaches 1.79e9 IV/s at machine precision (9.3e-14 max relative error vs. the reference C solver); end-to-end label generation sustains 48.9M/s on synthetic chains and 16.6M/s on SPX OptionMetrics. In a HyperIV-style one-day reproduction on SPX, PIVOT-augmented objectives Pareto-dominate the baselines, reducing held-out price MAE by up to 43.4% and the strongest three-seed gated objective improving price MAE by 38.8% and IV MAE by 21.3% jointly; cross-asset results on RUT, VIX, and NDX show directional price-MAE gains of 40.1%, 24.2%, and 16.7%, while an ungated IV-roundtrip control collapses to a degenerate near-zero surface, confirming the gate as a correctness contract rather than a tuning knob.

Simulation based solvers for optimal stopping problems must discretize the stopping decision. Under classical dynamic programming, a coarse exercise grid with only a few stopping opportunities can materially undervalue the optimal expected reward, whereas on a very fine grid, approximation errors accumulate through the backward recursion. To remove this limitation, we develop a new reinforcement-learning inspired algorithm that enables us to learn the exercise rule at arbitrarily fine time resolution. Our CARLOS (Continuous-time Adaptive Reinforcement Learning for Optimal Stopping) algorithm utilizes an aggregate deep neural network (ADNN) to learn a joint space-time decision boundary. Starting from a coarse time grid, we progressively increase the frequency of stopping opportunities, while in parallel training the ADNN to refine its timing-value estimates. We moreover design an adaptive sampling strategy that gradually concentrates training effort near the stopping boundary. Benchmarked results show that CARLOS delivers higher prices than existing Bermudan solvers, approaching the American upper bound, and achieves high computational efficiency relative to non-RL comparators.

This paper extends classical conformal frameworks for constructing prediction intervals with global marginal coverage $1-\alpha$ to intervals that provide explicitly calibrated guarantees for the upper and lower tails separately. Focusing on split conformal prediction, we first construct lower and upper one-sided conformal intervals that achieve marginal validity, and then derive the induced two-sided interval by intersection. Theoretical results prove both tail-specific and global marginal coverage of the induced two-sided interval. Results are presented first for the exchangeable setting, where coverage has finite-sample guarantees, and then for non-exchangeable data, where guarantees are asymptotic. Simulation studies show that the proposed approach achieves improved directional calibration relative to classical two-sided intervals, especially relevant in skewed data. Finally, the benefit of the proposed framework is showcased in a financial application, where one aims for return maximization while seeking strict control on the left tail.

Short-dated index options make scheduled macro-announcement risk visible in market prices, but visibility does not imply identification: a flexible no-event surface fitted to event-spanning quotes can absorb event premia, while a jump calibrated without event-spanning quotes is unidentified. To separate the continuous surface from the scheduled jump, we model Federal Open Market Committee (FOMC) decisions, Consumer Price Index (CPI) releases, and nonfarm payroll (NFP) reports as deterministic-time jumps in risk-neutral option pricing and propose a non-spanning identification protocol. Non-spanning expiries identify the no-event volatility surface, event-spanning training quotes calibrate the scheduled jump, and held-out event-spanning quotes are used only for pricing evaluation. On PM-settled S\&P 500 index (SPX) options from May 2022 to August 2025, Gaussian and two-component mixture jumps improve held-out event-spanning pricing, with the clearest gains in robust median pricing errors and in event-volatility option combinations (straddles and strangles) rather than directional risk reversals. A contaminated-surface stress test confirms the identification concern: allowing event-spanning training quotes into the no-event surface fit produces strong held-out performance by absorbing event premia rather than identifying scheduled jump risk. An amortized mixture density network (MDN) benchmark shows limited cross-event transfer: pure leave-one-event-out amortization reduces implied-volatility errors but not mean dollar or mean spread-normalized pricing errors, while the scale-calibrated variant restores Gaussian-level performance yet remains below event-specific mixture calibration. Scheduled-jump identification is strongest for CPI and FOMC and weaker for NFP.

We develop a dynamic stochastic model of markets with an externality and multiple trading frictions, and cap-and-trade as the leading application. Slow participation, limited intermediation, and heterogeneous information interact in equilibrium: agents choose costly market access, access determines residual compliance demand, intermediary constraints translate residual demand into a surrender-month premium, and the premium feeds back into access incentives. These interactions shape how effectively the market corrects the externality. We characterize access choices in closed form, prove that the equilibrium premium is unique, and show that endogenous access dampens the response to each friction in isolation, while the interaction of multiple frictions is non-additive and can amplify the price response. We quantify the model using 2.7 million EU ETS registry transactions and compliance records from 2005-2021. About 40% of operators do not trade annually, purchases concentrate in April when returns are systematically high, and operator flow predicts future returns.

This paper presents a comprehensive study on the use of ensemble Reinforcement Learning (RL) models in financial trading strategies, leveraging classifier models to enhance performance. By combining RL algorithms such as A2C, PPO, and SAC with traditional classifiers like Support Vector Machines (SVM), Decision Trees, and Logistic Regression, we investigate how different classifier groups can be integrated to improve risk-return trade-offs. The study evaluates the effectiveness of various ensemble methods, comparing them with individual RL models across key financial metrics, including Cumulative Returns, Sharpe Ratios (SR), Calmar Ratios, and Maximum Drawdown (MDD). Our original experimental results demonstrate that ensemble methods often outperform base models in terms of risk-adjusted returns, providing better management of drawdowns and overall stability. However, both the original analysis and the additional reproduction reported in this version show that ensemble performance is sensitive to the choice of variance threshold \(\tau\), classifier group, RL-agent pair, and market universe. The reproduction evidence strengthens the conclusion that classifier-assisted ensemble selection can improve robustness, while also clarifying that the advantage is conditional rather than automatic across all datasets. This study emphasizes the value of combining RL with classifiers for adaptive decision-making, with implications for financial trading, robotics, and other dynamic environments.

In many insurance contexts, dependence between risks of a portfolio may arise from their frequencies. We investigate a dependent risk model in which we assume the vector of count variables to be a tree-structured Markov random field with Poisson marginals. The tree structure translates into a wide variety of dependence schemes. We study the global risk of the portfolio and the risk allocation to all its constituents. We provide asymptotic results for portfolios defined on infinitely growing trees. To illustrate its flexibility and computational scalability to higher dimensions, we calibrate the risk model on real-world extreme rainfall data and perform a risk analysis.

Cryptocurrency portfolio management requires the fusion of heterogeneous multi-modal signals, including structured price and on-chain time series, unstructured news text, and technical indicators, under high-volatility and real-time constraints. While deep learning approaches show predictive capability, their opacity limits practical adoption, and single large language model (LLM) agents struggle to process the breadth of modality-specific inputs needed for robust decision-making. We propose a multi-agent system (MAS) framework in which three modality-specialised agents, a Crypto Agent for market dynamics, a News Agent for weekly news sentiment, and a Trading Agent for signal fusion and portfolio execution, decompose the task across three communication architectures: hierarchical, collaborative, and debate. We evaluate four capability configurations: zero-shot, chain-of-thought (CoT), retrieval-augmented generation (RAG), and skill-augmented. In a 52-week backtest over calendar year 2025 across the top 15 L1 blockchain native cryptocurrencies by market capitalisation as of January 2025, the best configuration, Hierarchical (Skill), achieves a cumulative return of 133.52% and a Sharpe ratio of 1.502, outperforming single-agent variants, passive benchmarks, and deep learning baselines. An ablation study identifies the Crypto Agent as the most critical component, with its removal reducing cumulative return by 42.57 percentage points. A cross-model comparison further shows that MAS outperforms the single-agent baseline under GPT-4o, GPT-5, and Claude Sonnet 4.5, suggesting that the benefit of multi-agent coordination is model-agnostic. Unlike black-box deep learning models, every portfolio decision is traceable to explicit agent reasoning, offering an interpretable and effective approach to multi-modal cryptocurrency portfolio management.

Model risk in credit portfolio models is a serious issue for banks but has so far not been tackled comprehensively. We will demonstrate how to deal with uncertainty in all model parameters in an all-embracing, yet easy-to-implement way.